regex for dataframe syntax

regex_df.py

import sys
import re

# construct regex here and export python regex: https://www.debuggex.com

# TODO make regex ignore white space where it doesn't matter

# first case: df[['col'...]] <-> df[c('col'...)] 
list_re = "\\s{0,}\\[\\s{0,}('\\w{1,}'){1,}\\s{0,}(,\\s{0,}'\\w{1,}'){0,}\\s{0,}\\]"
list_vars = re.compile(list_re)

# R: c()
list_re_r = "c\\(('\w{1,}'){1,}(,\\s{0,}'\w{1,}'){0,}\\)"
list_vars_r = re.compile(list_re_r)

# recognizes df[...] syntax
subset_cols_re = "df\\s{0,}\\[" + list_re + "\\]"
subset_cols = re.compile(subset_cols_re)
subset_cols_re_r = "df\\[" + list_re_r + "\\]"
subset_cols_r = re.compile(subset_cols_re_r)